CoolFace
Modelpublic

RichardErkhov/Gweizheng_-_Marcoro14-7B-dare-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes472downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Marcoro14-7B-dare - GGUF

  • —Model creator: https://huggingface.co/Gweizheng/
  • —Original model: https://huggingface.co/Gweizheng/Marcoro14-7B-dare/
NameQuant methodSize
Marcoro14-7B-dare.Q2_K.ggufQ2_K2.53GB
Marcoro14-7B-dare.IQ3_XS.ggufIQ3_XS2.81GB
Marcoro14-7B-dare.IQ3_S.ggufIQ3_S2.96GB
Marcoro14-7B-dare.Q3_K_S.ggufQ3KS2.95GB
Marcoro14-7B-dare.IQ3_M.ggufIQ3_M3.06GB
Marcoro14-7B-dare.Q3_K.ggufQ3_K3.28GB
Marcoro14-7B-dare.Q3_K_M.ggufQ3KM3.28GB
Marcoro14-7B-dare.Q3_K_L.ggufQ3KL3.56GB
Marcoro14-7B-dare.IQ4_XS.ggufIQ4_XS3.67GB
Marcoro14-7B-dare.Q4_0.ggufQ4_03.83GB
Marcoro14-7B-dare.IQ4_NL.ggufIQ4_NL3.87GB
Marcoro14-7B-dare.Q4_K_S.ggufQ4KS3.86GB
Marcoro14-7B-dare.Q4_K.ggufQ4_K4.07GB
Marcoro14-7B-dare.Q4_K_M.ggufQ4KM4.07GB
Marcoro14-7B-dare.Q4_1.ggufQ4_14.24GB
Marcoro14-7B-dare.Q5_0.ggufQ5_04.65GB
Marcoro14-7B-dare.Q5_K_S.ggufQ5KS4.65GB
Marcoro14-7B-dare.Q5_K.ggufQ5_K4.78GB
Marcoro14-7B-dare.Q5_K_M.ggufQ5KM4.78GB
Marcoro14-7B-dare.Q5_1.ggufQ5_15.07GB
Marcoro14-7B-dare.Q6_K.ggufQ6_K5.53GB
Marcoro14-7B-dare.Q8_0.ggufQ8_07.17GB

Original model description: --- license: apache-2.0 tags:

  • —merge
  • —mergekit
  • —lazymergekit
  • —samir-fama/SamirGPT-v1
  • —abacusai/Slerp-CM-mist-dpo
  • —EmbeddedLLM/Mistral-7B-Merge-14-v0.2 ---

Marcoro14-7B-dare

Marcoro14-7B-dare is a merge of the following models using mergekit:

🧩 Configuration

\```yaml models:

  • —model: mistralai/Mistral-7B-v0.1 # No parameters necessary for base model
  • —model: samir-fama/SamirGPT-v1 parameters: density: 0.53 weight: 0.4
  • —model: abacusai/Slerp-CM-mist-dpo parameters: density: 0.53 weight: 0.3
  • —model: EmbeddedLLM/Mistral-7B-Merge-14-v0.2 parameters: density: 0.53 weight: 0.3 mergemethod: dareties basemodel: mistralai/Mistral-7B-v0.1 parameters: int8mask: true dtype: bfloat16 \```